Gilad Gal
Principal Product Manager I at Elastic
One setting for production vector search: How vectordb_document mode tunes Elasticsearch automatically
Benchmarks across four datasets show how one index setting applies bfloat16 vector quantization, cache preloading and parallel merges to improve vector search throughput and decrease storage.
Elasticsearch now with BBQ by default & ACORN for filtered vector search
Explore how Elasticsearch's vector search now delivers better results faster, and at a lower cost.
Retrieval of originating information in multi-vector documents
Learn about multi-vector documents in Elasticsearch, their use cases, and how to link original context to a multi-vector document.
